© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 27253
    Prev
    Next
    INDEX
    Explanations

    syntactic and structural elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.18
    1.0%
    50
    +0.14
    0.8%
    38
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.18
    0.05
    50
    +0.14
    0.04
    303
    +0.12
    0.05
    Negative Logits
    uits
    -1.99
    iti
    -1.97
    iest
    -1.93
    itti
    -1.83
    aby
    -1.72
    ously
    -1.72
    ised
    -1.71
    otal
    -1.69
    ête
    -1.62
    uit
    -1.59
    POSITIVE LOGITS
    Īĺ
    2.47
    ¾
    2.36
    ¯
    2.31
    ¤
    2.29
    ŀ
    2.25
    ĸ´
    2.21
    ±
    2.18
    IJ
    2.08
    ¿
    2.08
    Ģ
    2.06
    Activations Density 0.350%

    No Known Activations